The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes platform-specific CLI scripts (scripts/anysearch_cli.py, anysearch_cli.js, anysearch_cli.ps1, anysearch_cli.sh) to perform search and content extraction operations.
[EXTERNAL_DOWNLOADS]: Installation instructions guide users to download the skill package from its official GitHub repository and install the requests library for the Python-based CLI runtime.
[DATA_EXFILTRATION]: Search queries and extracted web page contents are transmitted to the api.anysearch.com endpoint. This is the intended primary function of the skill and is performed against the vendor's infrastructure.
[PROMPT_INJECTION]: As a tool designed to retrieve and process external web content (via the extract and search commands), the skill provides a surface for indirect prompt injection. Maliciously crafted instructions on third-party websites could potentially influence agent behavior when processed.
Ingestion points: API response content retrieved via CLI scripts in the scripts/ directory.
Boundary markers: The skill returns content formatted as Markdown or JSON for agent consumption.
Capability inventory: Subprocess execution of bundled CLI tools for network communication and data retrieval.
Sanitization: The scripts parse structured JSON-RPC responses and extract specific text fields before returning data to the agent.

anysearch